Lorem ipsum dolor sit amet, consectetur adipiscing elit. Integer eleifend tellus eget augue porttitor tempus. Donec sit amet dapibus orci, placerat convallis nisi. Sed massa risus, pellentesque non interdum sit amet, euismod at ligula. Maecenas nec tempor dolor, eu egestas erat. Suspendisse id nulla eget dui facilisis congue. Nunc eget nulla et lorem pellentesque lacinia imperdiet a orci. Donec ut risus ut nisi laoreet varius et nec massa. Nulla in diam eget nibh tempus lobortis sit amet in velit. Phasellus non nulla felis. Quisque et fermentum eros. In non dui dignissim, congue mi eu, aliquet nulla.

Fusce bibendum vel mauris id semper. Praesent euismod orci vel quam interdum, a porttitor augue cursus. Morbi et ornare nisi. Proin porttitor nulla non mauris consectetur tristique. Ut eget hendrerit metus, sollicitudin vulputate risus. Curabitur euismod tortor ac nulla scelerisque hendrerit. Nullam dapibus lobortis turpis ut mattis. Donec sodales vehicula lectus vitae egestas. Donec.

Xinyue Sheng and collaborators have authored a paper published in the June 2024 edition of MNRAS. NEural Engine for Discovering Luminous Events (NEEDLE): identifying rare transient candidates in real time from host galaxy images.

Known for their efficiency in analysing large data sets, machine learning-based classifiers have been widely used in wide-field sky survey pipelines. The Vera C. Rubin Observatory Legacy Survey of Space and Time (LSST) will generate millions of real-time alerts every night, enabling the discovery of large samples of rare events. Identifying such objects soon after explosion will be essential to study their evolution. This requires a machine learning framework that makes use of all the information available, including light curve, host galaxy and other contextual data.

https://academic.oup.com/mnras/article/531/2/2474/7685960?rss=1

Using ~5400 transients from the ZTF Bright Transient Survey as training and testing data, we develop NEEDLE, a novel hybrid (convolutional neural network + dense neural network) classifier to select for two rare classes with strong environmental preferences: superluminous supernovae (SLSNe) preferring dwarf galaxies, and tidal disruption events (TDEs) occurring in the centres of nucleated galaxies.

Our network is designed with LSST in mind and we expect performance to improve further with the higher resolution images and more accurate transient and host photometry that will be available from Rubin. Our system is currently deployed as an annotator on the UK alert broker, Lasair, to provide predictions to the community in real time.